[Gluster-devel] Performance issue

Ben Mok benmok at powerallnetworks.com
Thu Jul 17 08:11:54 UTC 2008


Hi Avati and Brent,

 

Thank you for your information! I have several questions about 1.4

1.       the last version is 1.4.0qa29, do new translator hash is available
in this version? 

2.       I just installed 1.4,  can I use old conf files which are used in
1.3 9 ? when I use old conf on client side, it can't start, log showed:

 

2008-07-17 15:33:38 D [unify.c:4312:init] storage-unify: namespace node
specified as afr-ns

2008-07-17 15:33:38 D [scheduler.c:45:get_scheduler] scheduler: attempt to
load file rr.so

2008-07-17 15:33:38 D [unify.c:4388:init] storage-unify: Child node count is
2

2008-07-17 15:33:38 C [unify.c:4441:init] storage-unify: Initializing
scheduler failed, Exiting

2008-07-17 15:33:38 E [xlator.c:261:xlator_init_rec] xlator: 'storage-unify'
init() failed. Check spec file.

2008-07-17 15:33:38 E [glusterfs.c:650:main] glusterfs: Error while
initializing translators. Exiting

 

I checked spec file in doc/examples/unify.vol , it is same as version 1.3 

 

3.       How to migrate the version from 1.3 to 1.4 ? Do it support on line
migration? 

 

Thanks again!  Your help is really appreciated. 

 

Ben 

  _____  

From: anand.avati at gmail.com [mailto:anand.avati at gmail.com] On Behalf Of
Anand Avati
Sent: Thursday, July 17, 2008 1:56 PM
To: Brent A Nelson
Cc: Ben Mok; gluster-devel at nongnu.org
Subject: Re: [Gluster-devel] Performance issue

 

 

FYI, the 1.4 branch is much more efficient handling metadata operations
(switched from ASCII protocol to binary), so it is significantly faster in
situations involving large numbers of small files.  It's not in an official
release yet, unfortunately, but it does work nicely.

Perhaps the GlusterFS developers will consider doing an intermediate release
with this improvement or make it an option in 1.3 (probably too big a
change, though, and would be difficult reworking the code to make it
optional), as the first official 1.4 release is probably still a ways
away...


Porting the binary protocol and nbio (which came hand-in-hand into 1.4) will
be pretty disruptive in the 1.3 series. We are working hard on getting 1.4
out soon. 

 


PS The developers are also working towards eliminating the namespace
requirement for unify/stripe; this could be a significant improvement, as
well.


Currently only unify needs namespace. stripe does not. The new branch will
have unify as is (with the namespace etc) but a new translator which will be
a functional replacement to unify will be introduced. This new translator
(hash) internally builds a distributed hash table over the storage servers
improving the FS performance significantly. The DHT is similar in concept to
many of the popular DHT algos, and hashes the filename and stores the file
on the hashed node. So functionally, it is similar to unify (directory
structure is replicated, file exists on only one node) but the internals are
quite different, without a namespace too.

avati

No virus found in this incoming message.
Checked by AVG - http://www.avg.com 
Version: 8.0.138 / Virus Database: 270.5.0/1556 - Release Date: 16/7/2008
16:56



More information about the Gluster-devel mailing list